# Acknowledgements & Credits
Boring-Gemini stands on the shoulders of giants. We gratefully acknowledge the following individuals, organizations, and research that inspired this project.
## Concepts & Methodologies
* **Vibe Coding**: Detailed by **Andrej Karpathy** (February 2025), "Vibe Coding" describes the shift from writing syntax to guiding AI behavior through natural language and intent. This project is a practical implementation of that philosophy.
* **Shadow Mode**: Use of "Shadow Mode" for safe AI operations is standard in deployment engineering (e.g., Tesla Autopilot, Canary Deployments). Our implementation adapts this for agentic coding safety.
* **LLM-as-a-Judge**: The evaluation framework in `boring.judge` is inspired by research into using LLMs to evaluate other models.
* *Reference*: Jiang, X. et al. (2024). "A Survey on LLM-as-a-Judge". arXiv:2411.15594.
* *Reference*: Zheng, L. et al. (2023). "Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena". arXiv:2306.05685.
## Technologies & Standards
* **Model Context Protocol (MCP)**: This project implements the [Model Context Protocol](https://modelcontextprotocol.io), an open standard developed by **Anthropic**.
* **Google Gemini**: This project is built to control the [Gemini CLI](https://pypi.org/project/google-genai/), a product of **Google DeepMind**.
* *Disclaimer*: This is an unofficial tool and is not affiliated with or endorsed by Google.
## Open Source Ecology
* **Code of Conduct**: Adapted from the [Contributor Covenant](https://www.contributor-covenant.org), version 1.4.
* **License**: Licensed under the **Apache License, Version 2.0**.
---
*Verified Compliance Audit: 2026-01-09*
